dancing-bear-show/dancing-bear

code-review

Adversarial swarm PR code review. Fetches diff, sweeps for relevant concerns, fans out per-file validators, consolidates findings, and posts inline GitHub comments.

review-and-fix

Run adversarial swarm review then auto-fix all findings in parallel. Use when the user says "review and fix", "swarm fix", or wants review and fix in one shot.

review-fix-threads

Fetch every PR review thread (Copilot and human), triage each one, fix them in parallel, verify with happy/sad-path coverage, refresh the PR title and description, then reply to and resolve every thread. Use when the user says "address the review threads",…

workflow

Execute a workflow definition. Parses YAML, compiles DAG, walks parallel groups, spawns agents per stage, handles human gates and validation.

decompose

Split an oversized Python file into smaller focused modules, updating all call sites directly (no re-export facades). Use when a file is too large to review or maintain comfortably.

dancing-bear-rules

Shared project rules for all dancing-bear agents. Covers CLI conventions, credential protection, output helpers, coding standards, and the plan→dry-run→apply pattern.

ci-debug

Diagnose and fix GitHub Actions CI failures. Given a URL, PR number, or "CI is failing", parses logs, identifies root cause, fixes locally, and verifies. Use when CI is red and you need to get it green.

expand-coverage

Analyze test coverage gaps on changed or specified files, spawn tester agents to write tests, and verify improvement. Use when you need to get coverage above 80% on new code or expand coverage on existing modules.

open-pr

Comprehensive pre-PR validation and pull request creation. Runs type checking (mypy), linting (qlty), tests, coverage validation, generates PR description from template, and creates the PR. Use when ready to open a PR for review.

optimize-code-complexity

Cognitive complexity refactoring. Identifies functions exceeding complexity thresholds and applies refactoring patterns (dispatch tables, helper extraction, early returns). Use to improve code readability and maintainability.

optimize-code-coverage

Test quality and coverage verification. Checks test structure, helper reuse (fixtures/factories), parametrization, assertions, and coverage gaps. Use after writing tests to ensure quality and coverage targets are met (80%+ on new code).

optimize-code-reuse

Code duplication and helper extraction audit. Identifies reimplemented utilities, promotes shared helpers, extracts constants, and consolidates domain utilities. Use to reduce code duplication and improve maintainability.

optimize-code-security

Security and credential masking audit. Checks for hardcoded credentials, unmasked output, proper secret handling, and secure API patterns. Use to prevent credential leaks and ensure secure data handling before PR.

optimize-code

Post-implementation code optimization pass. Checks shared utility reuse (local then core), OO abstractions, bare string literals, cognitive complexity, test quality (fixtures/factories/shared helpers), dataclasses over dicts, dead code, architecture…

select-workflow

Interactively select the right workflow for a task. Describe what you want to do in plain language and get back the matching workflow, required params, and a ready-to-run /workflow invocation. Use when you know what you want to accomplish but aren't sure…

split-workflow-stages

Split oversized workflow stages into smaller single-responsibility stages. Audits a workflow YAML for stages with multiple responsibilities (long descriptions, multiple data sources, mixed gather+transform logic), plans splits with human approval, applies…

validate-workflow

Validate workflow YAML files and skill docs for structural correctness and real CLI command references. Runs workflow lint with command probing, checks that skill examples use correct --params syntax, and verifies referenced stage names match the compiled…

write-workflow

Author a new workflow YAML from a plain-language description. Interviews the user for requirements, drafts the YAML using project conventions, validates it with the workflow engine, and writes the final file. Use when you want to create a new workflow.

critique

Run an adversarial Opus critique against a design doc, a workflow YAML, a set of files, or the current diff, using the plan-critic fragment (internal-consistency check -> adversarial critique -> fact-check -> consolidated summary -> human gate -> optional…

otel-doctor

Diagnose why this repo's local OTel telemetry pipeline isn't working (Colima down, port collision, container not running, env vars not set, or no data flowing) and fix the first failing layer. Use when `telemetry otel <cmd>` reports "OpenTelemetry…

improve-decompose-sweep

Calibrate the decompose-sweep workflow after a completed run. Reads telemetry, identifies patterns (defer reasons, overshoot rate, test failures), proposes threshold and heuristic changes backed by data, patches the workflow YAML, and reports a summary.

familiarize

Preload repo context for the dancing-bear personal-assistants codebase. Use when the user runs /familiarize, says "get familiar with this repo", or starts a new session and wants Claude oriented before making changes.